Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jan 31:2022:8158634.
doi: 10.1155/2022/8158634. eCollection 2022.

Account of Deep Learning-Based Ultrasonic Image Feature in the Diagnosis of Severe Sepsis Complicated with Acute Kidney Injury

Yi Lv  1 , Zhijia Huang  1
Affiliations

Account of Deep Learning-Based Ultrasonic Image Feature in the Diagnosis of Severe Sepsis Complicated with Acute Kidney Injury

Yi Lv et al. Comput Math Methods Med. .

Retraction in

Abstract

This study was aimed at analyzing the diagnostic value of convolutional neural network models on account of deep learning for severe sepsis complicated with acute kidney injury and providing an effective theoretical reference for the clinical use of ultrasonic image diagnoses. 50 patients with severe sepsis complicated with acute kidney injury and 50 healthy volunteers were selected in this study. They all underwent ultrasound scans. Different deep learning convolutional neural network models dense convolutional network (DenseNet121), Google inception net (GoogLeNet), and Microsoft's residual network (ResNet) were used for training and diagnoses. Then, the diagnostic results were compared with professional image physicians' artificial diagnoses. The results showed that accuracy and sensitivity of the three deep learning algorithms were significantly higher than professional image physicians' artificial diagnoses. Besides, the error rates of the three algorithm models for severe sepsis complicated with acute kidney injury were significantly lower than professional physicians' artificial diagnoses. The areas under curves (AUCs) of the three algorithms were significantly higher than AUCs of doctors' diagnosis results. The loss function parameters of DenseNet121 and GoogLeNet were significantly lower than that of ResNet, with the statistically significant difference (P < 0.05). There was no significant difference in training time of ResNet, GoogLeNet, and DenseNet121 algorithms under deep learning, as the convergence was reached after 700 times, 700 times, and 650 times, respectively (P > 0.05). In conclusion, the value of the three algorithms on account of deep learning in the diagnoses of severe sepsis complicated with acute kidney injury was higher than professional physicians' artificial judgments and had great clinical value for the diagnoses and treatments of the disease.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
DenseNet121 convolutional neural network model.
Figure 2
Figure 2
The inception module of GoogLeNet.
Figure 3
Figure 3
ResNet convolutional neural network model.
Figure 4
Figure 4
Ultrasonic image results of severe sepsis complicated with acute kidney injury.
Figure 5
Figure 5
Comparison of accuracy, specificity, and sensitivity between the three algorithms and professional physicians. Note: ∗ represented significant differences: P < 0.05.
Figure 6
Figure 6
Comparison of the error rates among the three algorithms and professional physicians. Note: ∗ represented significant differences: P < 0.05.
Figure 7
Figure 7
ROC curve results of the three algorithms and diagnoses by professional physicians.
Figure 8
Figure 8
Comparison results of AUCs between the three algorithms and professional doctors' diagnoses. Note: ∗ represented significant differences: P < 0.05.
Figure 9
Figure 9
Loss function of the three algorithm models.
Figure 10
Figure 10
Comparison results of training time and parameter number of the three algorithms. Note: ∗ represented significant differences: P < 0.05.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Huang M., Cai S., Su J. The pathogenesis of sepsis and potential therapeutic targets. International Journal of Molecular Sciences . 2019;20(21):p. 5376. doi: 10.3390/ijms20215376. PMID: 31671729; PMCID: PMC6862039. - DOI - PMC - PubMed
    1. Salomão R., Ferreira B. L., Salomão M. C., Santos S. S., Azevedo L. C. P., Brunialti M. K. C. Sepsis: evolving concepts and challenges. Braz J Med Biol Res . 2019;52(4):p. e8595. doi: 10.1590/1414-431X20198595. Epub 2019 Apr 15. PMID: 30994733; PMCID: PMC6472937. - DOI - PMC - PubMed
    1. Hu M., Zhong Y., Xie S., Lv H., Lv Z. Fuzzy system based medical image processing for brain disease prediction. Frontiers in Neuroscience . 2021;30(15, article 714318) doi: 10.3389/fnins.2021.714318. PMID: 34393718; PMCID: PMC8361453. - DOI - PMC - PubMed
    1. Font M. D., Thyagarajan B., Khanna A. K. Sepsis and septic shock - basics of diagnosis, pathophysiology and clinical decision making. The Medical Clinics of North America . 2020;104(4):573–585. doi: 10.1016/j.mcna.2020.02.011. Epub 2020 May 12. PMID: 32505253. - DOI - PubMed
    1. Esposito S., De Simone G., Boccia G., De Caro F., Pagliano P. Sepsis and septic shock: new definitions, new diagnostic and therapeutic approaches. J Glob Antimicrob Resist. . 2017;10:204–212. doi: 10.1016/j.jgar.2017.06.013. Epub 2017 Jul 22. PMID: 28743646. - DOI - PubMed

Publication types

MeSH terms